Basic Statistics

The data is 48.8 Mb in size. There are 20,715 rows and 290 columns (features). Of all 290 columns, 8 are discrete, 282 are continuous, and 0 are all missing. There are 193,630 missing values out of 6,007,350 data points.


Metadata (Table)


Data Structure (Network Graph)


Missing Values

The following graph shows the distribution of missing values.


Data Distribution

Continuous Features (Histogram)


Continuous Features (Density)


Discrete Features (Bar Chart)

## 6 columns ignored with more than 50 categories.
## DAY_0: 63 categories
## MAC: 20204 categories
## CLY_ACCOUNT_NUMBER: 20103 categories
## SAA_ACCOUNT_NUMBER: 20103 categories
## CMTS: 125 categories
## SERVICE_GROUP: 1004 categories




Correlation Analysis

Version 1

## 6 features with more than 20 categories ignored!
## DAY_0: 63 categories
## MAC: 20204 categories
## CLY_ACCOUNT_NUMBER: 20103 categories
## SAA_ACCOUNT_NUMBER: 20103 categories
## CMTS: 125 categories
## SERVICE_GROUP: 1004 categories




Version 2

## Error in hclustfun_row(dist_x): NA/NaN/Inf in foreign function call (arg 11)